Senior Inference Engineer

📋 Description

• Build and deploy production-grade LLM inference systems across GPU machines
• Design and operate model-serving infrastructure with vLLM, SGLang, TensorRT-LLM
• Optimize workloads for latency, throughput, reliability, and cost
• Apply quantization, batching, caching, and routing to boost inference performance
• Develop robust production infra using Python or Golang
• Collaborate with CTO and Product to evolve the inference platform and roadmap

🎯 Requirements

• Significant experience building/operating production software or infra systems
• Production deployment of large language models with vLLM, SGLang, TensorRT-LLM or similar
• Expertise in quantization, batching, caching, routing
• Strong Python or Golang production-ready programming skills
• Understanding of production inference architectures and end-to-end user request flow
• Excellent problem-solving and communication skills

🎁 Benefits

• Equity and competitive compensation
• Health/dental/vision/life insurance with dependents coverage where available
• Flexible, outcome-oriented schedule
• Remote-first with globally distributed team
• Ownership over architecture and long-term roadmap
• Collaboration with senior leadership and Product teams